Qwen2.5-Math-RM-72B
Special purpose
The two models of interest are the Qwen2.5-72B-Instruct and Qwen2.5-Math-RM-72B by Qwen. Good reward models are far and few between these days, especially for Math. The Instruct model has been scoring extremely high on evals and some vibe checks.
Adoption · Hugging Face
RAM score
Relative Adoption Metric not applicable.
Hugging Face Downloads
40.7K
last 30d
894.7K
all time
HF Likes
89
Relative Adoption Metric not applicable.
Related Models